Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases associated with mathematical relationships and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical notation with symbols and variables

    np_acts-logits-general · gemini-2.0-flash

    mathematical variables and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.68
    AsUp
    -0.67
    crollView
    -0.65
     bezeichneter
    -0.63
    Pratique
    -0.63
     المعيارى
    -0.63
    ImageContext
    -0.62
    ՚
    -0.62
     useStyles
    -0.61
    %");
    -0.61
    POSITIVE LOGITS
     $
    2.08
     $\
    2.07
     $(
    1.39
     ${\
    1.33
     ${
    1.32
    $\
    1.22
     $|
    1.22
     $(\
    1.20
     $[
    1.19
     $-
    1.18
    Act Density 1.687%

    No Known Activations